针对图像超分辨率重建网络因结构冗杂、参数量增加导致的计算量过大、训练时间过长等问题，提出一种注意力引导的轻量级图像超分辨率网络（LAGNet）。LAGNet将随机初始化的自适应权重引入深度残差网络结构，更大限度地利用浅层特征信息。其次，提出注意力引导（AG）模块，该模块使用高效通道注意力（ECA）模块和空间分组增强（SGE）模块双支路并联结构，结合通道间关系和空间位置信息特征，利用注意力引导层动态调整两个分支的权重占比，准确获取高频特征信息。最后，使用全局级联连接，减少网络参数量并加快信息流通速度。使用L1损失函数，在加快收敛速度的同时防止梯度爆炸。在三个基准数据集上的测试结果表明：相比其他网络，LAGNet的峰值信噪比平均提高0.39 dB，模型参数量平均减少24%，加法操作量和乘法操作量平均减少62%；在图像视觉效果上整体更为清晰，细节纹理更自然。

A lightweight attention-guided super-resolution network (LAGNet) is proposed to address issues such as excessive computation and long training time caused by the redundant structure and increased parameters of image super-resolution reconstruction networks. First, the LAGNet introduces randomly initialized adaptive weights into the deep residual network structure to maximize the use of shallow feature information. Second, an attention guidance (AG) module uses the parallel structure of the efficient channel attention (ECA) model and the spatial group-wise enhance (SGE) model, combines the relationship between channels and the spatial location information characteristics, and employs the attention-guide layer to dynamically adjust the weight proportion of the two branches to obtain high-efficiency channel feature information. Finally, the global cascade connection is used to reduce network parameters and speed up information flow. The L1 loss function is used to accelerate convergence speed and prevent gradient explosion. The test results on the three benchmark datasets show that on average the peak signal-to-noise ratio of the LAGNet is increased by 0.39 dB, the model parameters are reduced by 24%, and the addition and multiplication operations are reduced by 62% compared with other networks; the overall visual effect of the image is clear and the detail texture is more natural.